{
  "best_global_step": 2958,
  "best_metric": 1.3441592454910278,
  "best_model_checkpoint": "/content/drive/MyDrive/mn_cpt_v3_ckpts_round1/checkpoint-2958",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2958,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03380662609871535,
      "grad_norm": 20.814611434936523,
      "learning_rate": 1.98e-05,
      "loss": 2.7703976440429687,
      "step": 100
    },
    {
      "epoch": 0.0676132521974307,
      "grad_norm": 8.971936225891113,
      "learning_rate": 1.9940845600356408e-05,
      "loss": 1.5906294250488282,
      "step": 200
    },
    {
      "epoch": 0.10141987829614604,
      "grad_norm": 8.869734764099121,
      "learning_rate": 1.9761702758358067e-05,
      "loss": 1.5138514709472657,
      "step": 300
    },
    {
      "epoch": 0.1352265043948614,
      "grad_norm": 7.827669143676758,
      "learning_rate": 1.9464727839372697e-05,
      "loss": 1.4664981079101562,
      "step": 400
    },
    {
      "epoch": 0.16903313049357674,
      "grad_norm": 14.620606422424316,
      "learning_rate": 1.9053505583930026e-05,
      "loss": 1.4547904968261718,
      "step": 500
    },
    {
      "epoch": 0.16903313049357674,
      "eval_loss": 1.4145898818969727,
      "eval_runtime": 103.2879,
      "eval_samples_per_second": 3.873,
      "eval_steps_per_second": 0.484,
      "step": 500
    },
    {
      "epoch": 0.2028397565922921,
      "grad_norm": 4.778053283691406,
      "learning_rate": 1.8532999795339947e-05,
      "loss": 1.4374798583984374,
      "step": 600
    },
    {
      "epoch": 0.23664638269100743,
      "grad_norm": 6.689450740814209,
      "learning_rate": 1.7909493422353473e-05,
      "loss": 1.437916259765625,
      "step": 700
    },
    {
      "epoch": 0.2704530087897228,
      "grad_norm": 5.550195693969727,
      "learning_rate": 1.7190512718613252e-05,
      "loss": 1.417725830078125,
      "step": 800
    },
    {
      "epoch": 0.30425963488843816,
      "grad_norm": 5.314340591430664,
      "learning_rate": 1.638473639435381e-05,
      "loss": 1.4123281860351562,
      "step": 900
    },
    {
      "epoch": 0.3380662609871535,
      "grad_norm": 4.626297473907471,
      "learning_rate": 1.5501890856967875e-05,
      "loss": 1.414586944580078,
      "step": 1000
    },
    {
      "epoch": 0.3380662609871535,
      "eval_loss": 1.380101203918457,
      "eval_runtime": 65.1956,
      "eval_samples_per_second": 6.135,
      "eval_steps_per_second": 0.767,
      "step": 1000
    },
    {
      "epoch": 0.37187288708586885,
      "grad_norm": 11.251319885253906,
      "learning_rate": 1.4552632804974546e-05,
      "loss": 1.4127529907226561,
      "step": 1100
    },
    {
      "epoch": 0.4056795131845842,
      "grad_norm": 5.304548263549805,
      "learning_rate": 1.354842059258024e-05,
      "loss": 1.4026646423339844,
      "step": 1200
    },
    {
      "epoch": 0.43948613928329955,
      "grad_norm": 5.564629077911377,
      "learning_rate": 1.2501375917571837e-05,
      "loss": 1.4003787231445313,
      "step": 1300
    },
    {
      "epoch": 0.47329276538201487,
      "grad_norm": 7.565065383911133,
      "learning_rate": 1.1424137502087119e-05,
      "loss": 1.3923248291015624,
      "step": 1400
    },
    {
      "epoch": 0.5070993914807302,
      "grad_norm": 4.881017208099365,
      "learning_rate": 1.0329708532460358e-05,
      "loss": 1.392799835205078,
      "step": 1500
    },
    {
      "epoch": 0.5070993914807302,
      "eval_loss": 1.3630108833312988,
      "eval_runtime": 64.591,
      "eval_samples_per_second": 6.193,
      "eval_steps_per_second": 0.774,
      "step": 1500
    },
    {
      "epoch": 0.5409060175794456,
      "grad_norm": 6.385213375091553,
      "learning_rate": 9.231299699674285e-06,
      "loss": 1.3879092407226563,
      "step": 1600
    },
    {
      "epoch": 0.5747126436781609,
      "grad_norm": 4.620737075805664,
      "learning_rate": 8.142169735053952e-06,
      "loss": 1.4032789611816405,
      "step": 1700
    },
    {
      "epoch": 0.6085192697768763,
      "grad_norm": 6.220205783843994,
      "learning_rate": 7.075465366072709e-06,
      "loss": 1.3808775329589844,
      "step": 1800
    },
    {
      "epoch": 0.6423258958755916,
      "grad_norm": 8.211082458496094,
      "learning_rate": 6.044062624140205e-06,
      "loss": 1.3779316711425782,
      "step": 1900
    },
    {
      "epoch": 0.676132521974307,
      "grad_norm": 5.718968868255615,
      "learning_rate": 5.060411419922684e-06,
      "loss": 1.387956085205078,
      "step": 2000
    },
    {
      "epoch": 0.676132521974307,
      "eval_loss": 1.3504174947738647,
      "eval_runtime": 39.7065,
      "eval_samples_per_second": 10.074,
      "eval_steps_per_second": 1.259,
      "step": 2000
    },
    {
      "epoch": 0.7099391480730223,
      "grad_norm": 3.7877399921417236,
      "learning_rate": 4.136385262304085e-06,
      "loss": 1.3782768249511719,
      "step": 2100
    },
    {
      "epoch": 0.7437457741717377,
      "grad_norm": 10.204033851623535,
      "learning_rate": 3.2831379350081883e-06,
      "loss": 1.3788711547851562,
      "step": 2200
    },
    {
      "epoch": 0.777552400270453,
      "grad_norm": 3.7870566844940186,
      "learning_rate": 2.5109688609172235e-06,
      "loss": 1.375047607421875,
      "step": 2300
    },
    {
      "epoch": 0.8113590263691683,
      "grad_norm": 4.114550590515137,
      "learning_rate": 1.8291987792544041e-06,
      "loss": 1.376358184814453,
      "step": 2400
    },
    {
      "epoch": 0.8451656524678837,
      "grad_norm": 3.9523532390594482,
      "learning_rate": 1.2460572363129009e-06,
      "loss": 1.3739906311035157,
      "step": 2500
    },
    {
      "epoch": 0.8451656524678837,
      "eval_loss": 1.3448355197906494,
      "eval_runtime": 26.8663,
      "eval_samples_per_second": 14.889,
      "eval_steps_per_second": 1.861,
      "step": 2500
    },
    {
      "epoch": 0.8789722785665991,
      "grad_norm": 7.049986362457275,
      "learning_rate": 7.685832478139521e-07,
      "loss": 1.3785447692871093,
      "step": 2600
    },
    {
      "epoch": 0.9127789046653144,
      "grad_norm": 8.738005638122559,
      "learning_rate": 4.025403319843302e-07,
      "loss": 1.3778578186035155,
      "step": 2700
    },
    {
      "epoch": 0.9465855307640297,
      "grad_norm": 8.873653411865234,
      "learning_rate": 1.5234693897625552e-07,
      "loss": 1.3746939086914063,
      "step": 2800
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 4.53987979888916,
      "learning_rate": 2.102311640604593e-08,
      "loss": 1.375147705078125,
      "step": 2900
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.3441592454910278,
      "eval_runtime": 26.9127,
      "eval_samples_per_second": 14.863,
      "eval_steps_per_second": 1.858,
      "step": 2958
    }
  ],
  "logging_steps": 100,
  "max_steps": 2958,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.3047023099032727e+18,
  "train_batch_size": 45,
  "trial_name": null,
  "trial_params": null
}